Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    common and specific types of use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     with
    0.30
     úpl
    0.29
     یا
    0.28
     ან
    0.27
    }{
    0.26
     cheered
    0.26
     as
    0.25
     or
    0.25
    หรือ
    0.25
     algodón
    0.25
    POSITIVE LOGITS
     types
    0.30
    types
    0.27
    类型的
    0.26
    異なる
    0.25
     parameters
    0.25
    種類の
    0.25
     પ્રકાર
    0.24
     topics
    0.24
     disciplines
    0.24
     metrics
    0.24
    Act Density 3.790%

    No Known Activations